Agent Memory Engine
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| project-root | No | Absolute path to the project root (command-line argument) | |
| MEMORY_ENGINE_PROJECT_ROOT | No | Absolute path to the project root (environment variable) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| retrieve_agent_contextA | Retrieve the smallest relevant set of persistent memory and grounded project knowledge before non-trivial coding work. Bootstraps the project automatically on first use. |
| inspect_memoryB | Progressively inspect a MemoryNode, its children, relations, and relevant evidence. Use after retrieve_agent_context when more depth is needed on a specific memory. |
| inspect_knowledgeC | Inspect a KnowledgeChunk or source-grounded file range within the target project. Paths are restricted to the project root. Content is redacted before output. |
| reflect_and_writeA | Report a completed validated task to the post-task reflection pipeline. The system decides whether and how to retain knowledge — agents cannot force memory creation directly. Do not call for trivial, failed, reverted, or unverified work. |
| memory_statusB | Return project health, bootstrap state, retrieval mode, memory counts, knowledge index status, and cache state. |
| refresh_project_knowledgeA | Explicit-use only. Trigger a safe incremental rescan of changed project sources. Not needed for normal workflow — indexing runs automatically on bootstrap. Returns a summary of changed, added, and removed sources. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| get_constraints | |
| get_architecture | |
| get_status | |
| get_recent_incidents | |
| get_memory_tree_summary | |
| get_agent_policy |
TDQS
Scored across 6 tools
Each tool has a distinct purpose: inspecting knowledge vs. memory vs. status vs. reflection vs. refresh vs. context retrieval. The descriptions clearly differentiate them, so an agent can easily select the appropriate tool.
Five tools follow a verb_noun pattern (e.g., inspect_knowledge, retrieve_agent_context), but memory_status uses a noun_noun format, which is a minor deviation. Overall, naming is mostly consistent and readable.
Six tools is well-scoped for an agent memory engine, covering the essential operations: inspection, status, reflection, refresh, and context retrieval. The count is neither too few nor excessive.
The tool set covers core workflows: reading memory/knowledge, monitoring status, triggering reflection, and refreshing knowledge. However, it lacks explicit tools for direct memory creation or deletion, relying on the reflection pipeline for writing, which may be a minor gap.